Steven Abney's area of research is computational linguistics, which encompasses language technology (machine translation, speech recognition, information extraction), digital linguistics, the language part of artificial intelligence, and computational psycholinguistics. His career has alternated between academic linguistic departments and computer science departments in industrial research labs. To his mind, language is an intrinsically computational system, and computational linguistics is linguistics. Languages are no less complex than subatomic particles, galaxies, or living cells, and they deserve to be studied with the kind of mathematical and computational sophistication that is taken for granted in physics, astronomy, or molecular biology.
The projects he is currently working on include language digitization (creating a multilingual corpus of aligned and analyzed text, as a digital form of language documentation & description, and as a platform to study unsupervised learning of machine translation systems) and dependency parsing (semi-supervised and unsupervised learning of dependency parsers, especially for languages with nonplanar dependency graphs). He is also interested in the following topics: semisupervised learning and spectral methods; information extraction, especially for biomed; partial parsing and deterministic parsing; grammatical inference; conversational agents; spoken language systems; and automated phonetic transcription.
Courses he regularly teaches include Computational Linguistics (Ling 441), Mathematics of Language (Ling 341), and Language and Information (Ling 702/EECS 597/SI 760).
- EECS (courtesy appointment)
Field(s) of Study
- Computational linguistics, especially parsing and semi-supervised learning